{"id":"W4388779961","doi":"10.1515/9781552384039-013","title":"Schema-Independent Retrieval from Heterogeneous Structured Text","year":2006,"lang":"en","type":"book-chapter","venue":"University of Calgary Press eBooks","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Schema (genetic algorithms); Information retrieval; Computer science; Natural language processing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00008540484,0.0003432166,0.0004762888,0.0001350693,0.0001178951,0.0000481173,0.001652136,0.0005211058,0.0000831727],"category_scores_gemma":[0.000004704226,0.0004216584,0.000264598,0.000006855552,0.0001393664,0.0001053863,0.001010472,0.0004590593,0.00001198994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001556111,"about_ca_system_score_gemma":0.0001557824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001382813,"about_ca_topic_score_gemma":0.0002268966,"domain_scores_codex":[0.9978711,0.00003192586,0.0002713487,0.0007570488,0.0008121945,0.0002564059],"domain_scores_gemma":[0.9981346,0.00005280186,0.000340515,0.001150606,0.0001853425,0.0001361826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002536427,0.00003525745,0.000008273209,0.0001368602,0.0006168427,0.001679126,0.00107893,0.0009445701,0.001479454,0.933484,0.001513214,0.05876984],"study_design_scores_gemma":[0.003070324,0.0002092408,0.00005703023,0.0005492999,0.0004547976,0.0000852375,0.0000139377,0.0783776,0.01431601,0.05997032,0.8406569,0.002239277],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0005276286,0.000400108,0.2446345,0.000007133973,0.0003001064,0.0002652851,0.00004934032,0.0001562089,0.7536597],"genre_scores_gemma":[0.01276163,0.0000366386,0.04668974,0.0000698569,0.0001917731,1.291543e-7,0.00005267795,0.00005530467,0.9401423],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8735137,"threshold_uncertainty_score":0.9998235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01868248501142599,"score_gpt":0.1843995664926585,"score_spread":0.1657170814812325,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}